Image registration for sequence of visual images captured by UAV

摘要

Unmanned aerial vehicles (UAVs) are regularly outfitted with payloads that include high resolution surveillance cameras. These surveillance systems have provided the military with the opportunity to monitor battlefields and remote terrain, carryout reconnaissance missions and track targets all from distant ground stations without endangering UAV operators. As with any remote sensing technology there are technical challenges that exist. The problem often arises where large sequences of images containing significant redundancies are being sent to the ground station processing systems and operators. Consequently, the ground station systems can become ldquoweighed downrdquo and operators can become overwhelmed. In addition, the decision making process of detection and recognition algorithms could be rendered ineffective because of the limited visual field of view of individual image frames. In this research image registration software is designed and implemented to integrate a sequence of visual images based on the modified scale-invariant feature transform (SIFT) algorithm. Since computational efficiency is a critical issue in any real-time interactive system, a modified version of the SIFT algorithm is devised and utilized in this work. Implementation and testing results of the developed software are obtained from real data collected from aerial footage and a collaborative camera network.